© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133719
    Prev
    Next
    INDEX
    Explanations

    du/duk

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    沘
    0.43
     بار
    0.42
     im
    0.42
    abhut
    0.40
    වර
    0.39
     SI
    0.39
    IVOS
    0.39
     meg
    0.38
    بار
    0.38
    淄
    0.38
    POSITIVE LOGITS
    Keefe
    0.39
    adu
    0.38
    検
    0.38
     Duffy
    0.38
    du
    0.38
    duck
    0.37
    кем
    0.37
     wal
    0.37
     ducks
    0.37
     Keys
    0.36
    Activations Density 0.005%

    No Known Activations